A comparison of complexity selection approaches for polynomials based on: vapnik-chervonenkis dimension, rademacher complexity and covering numbers

Authors:
Przemysław Klęsk
Affiliations:
Department of Methods of Artificial Intelligence and Applied Mathematics, West Pomeranian University of Technology, Szczecin, Poland
Venue:
ICAISC'12 Proceedings of the 11th international conference on Artificial Intelligence and Soft Computing - Volume Part II
Year:
2012

Citing 9
Cited 0

A generalization of Sauer's lemma

Journal of Combinatorial Theory Series A
The nature of statistical learning theory

The nature of statistical learning theory
Learning from Data: Concepts, Theory, and Methods

Learning from Data: Concepts, Theory, and Methods
Covering number bounds of certain regularized linear function classes

The Journal of Machine Learning Research
Rademacher and gaussian complexities: risk bounds and structural results

The Journal of Machine Learning Research
Feature selection, L1 vs. L2 regularization, and rotational invariance

ICML '04 Proceedings of the twenty-first international conference on Machine learning
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
Neural Network Learning: Theoretical Foundations

Neural Network Learning: Theoretical Foundations
The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

IEEE Transactions on Information Theory

Quantified Score

Hi-index	0.00

Visualization

Abstract

We compare and give some practical insights about several complexity selection approaches (under PAC model) based on: well known VC-dimension, and more recent ideas of Rademacher complexity and covering numbers. The classification task that we consider is carried out by polynomials. Additionally, we compare results of non-regularized and L2-regularized learning and its influence on complexity.